{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:24:50Z","timestamp":1792513490284,"version":"4.5.0"},"reference-count":279,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0160104"],"award-info":[{"award-number":["2022ZD0160104"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206172"],"award-info":[{"award-number":["62206172"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Committee of Science and Technology","award":["23YF1462000"],"award-info":[{"award-number":["23YF1462000"]}]},{"name":"ERC","award":["LEGO-3D (850533)"],"award-info":[{"award-number":["LEGO-3D (850533)"]}]},{"DOI":"10.13039\/501100006360","name":"Bundesministerium f\u00fcr Wirtschaft und Energie","doi-asserted-by":"publisher","award":["19A19013O"],"award-info":[{"award-number":["19A19013O"]}],"id":[{"id":"10.13039\/501100006360","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DFG EXC","award":["2064\/1"],"award-info":[{"award-number":["2064\/1"]}]},{"name":"DFG EXC","award":["390727645"],"award-info":[{"award-number":["390727645"]}]},{"name":"German Federal Ministry of Education and Research"},{"name":"Tübingen AI Center","award":["01IS18039A"],"award-info":[{"award-number":["01IS18039A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3435937","type":"journal-article","created":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T13:53:57Z","timestamp":1722347637000},"page":"10164-10183","source":"Crossref","is-referenced-by-count":622,"title":["End-to-End Autonomous Driving: Challenges and Frontiers"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9500-5722","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"first","affiliation":[{"name":"OpenDriveLab, Shanghai AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6478-1166","authenticated-orcid":false,"given":"Penghao","family":"Wu","sequence":"additional","affiliation":[{"name":"OpenDriveLab, Shanghai AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3891-3230","authenticated-orcid":false,"given":"Kashyap","family":"Chitta","sequence":"additional","affiliation":[{"name":"University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6657-2499","authenticated-orcid":false,"given":"Bernhard","family":"Jaeger","sequence":"additional","affiliation":[{"name":"University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8151-3726","authenticated-orcid":false,"given":"Andreas","family":"Geiger","sequence":"additional","affiliation":[{"name":"University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9110-5534","authenticated-orcid":false,"given":"Hongyang","family":"Li","sequence":"additional","affiliation":[{"name":"OpenDriveLab, Shanghai AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01417"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref3","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pomerleau"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref5","first-page":"66","article-title":"Learning by cheating","volume-title":"Proc. Conf. Robot Learn.","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_20"},{"key":"ref8","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01178"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"ref12","article-title":"Policy pre-training for autonomous driving via self-supervised geometric modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref13","article-title":"CARLA autonomous driving leaderboard","year":"2022"},{"key":"ref14","article-title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Caesar"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197408"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_36"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/robotics12050127"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01530"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref22","first-page":"6119","article-title":"Trajectory-guided control prediction for end-to-end autonomous driving: A simple yet strong baseline","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00754"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.056"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10857"},{"key":"ref26","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref29","first-page":"726","article-title":"Safety-enhanced autonomous driving using interpretable sensor fusion transformer","volume-title":"Proc. Conf. Robot Learn.","author":"Shao"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02105"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00757"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00978"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340696"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01680"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"ref40","article-title":"Computer vision for autonomous vehicles: Problems, datasets and state-of-the-art","author":"Janai","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3043505"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3274536"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3192019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3002505"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3144867"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213246"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3134702"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref49","article-title":"A framework for behavioural cloning","volume":"15","author":"Bain","year":"1995","journal-title":"Mach. Intell."},{"key":"ref50","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Ziebart"},{"key":"ref51","article-title":"DAVE: Autonomous off-road vehicle control using end-to-end learning","author":"Lecun","year":"2004"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01671"},{"key":"ref53","first-page":"4105","article-title":"Active imitation learning: Formal and practical reductions to IID learning","volume":"15","author":"Judah","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref55","article-title":"Reinforcement and imitation learning via interactive no-regret learning","author":"Ross","year":"2014"},{"key":"ref56","article-title":"Meta learning framework for automated driving","author":"Sallab","year":"2017","journal-title":"1706.04038"},{"key":"ref57","first-page":"2564","article-title":"Fighting copycat agents in behavioral cloning from observation histories","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref58","first-page":"11123","article-title":"Keyframe-focused visual imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wen"},{"key":"ref59","first-page":"3029","article-title":"Object-aware regularization for addressing causal confusion in imitation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Park"},{"key":"ref60","first-page":"23723","article-title":"Fighting fire with fire: Avoiding DNN shortcuts through priming","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wen"},{"key":"ref61","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brown"},{"key":"ref62","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref63","article-title":"SQIL: Imitation learning via reinforcement learning with sparse rewards","author":"Reddy","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561411"},{"key":"ref65","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref66","first-page":"3815","article-title":"InfoGAIL: Interpretable imitation learning from visual demonstrations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341104"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00252"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01254"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_21"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref73","article-title":"An invitation to deep reinforcement learning","author":"Jaeger","year":"2023"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref76","article-title":"Distributed prioritized experience replay","author":"Horgan","year":"2018"},{"key":"ref77","first-page":"8242","article-title":"Towarddeeper deep reinforcement learning with spectral normalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bjorck"},{"key":"ref78","article-title":"Is deep reinforcement learning really superhuman on atari? Leveling the playing field","author":"Toromanoff","year":"2019"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01131"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103829"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_16"},{"key":"ref82","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hafner"},{"key":"ref83","article-title":"Mastering atari with discrete world models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hafner"},{"key":"ref84","first-page":"2455","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ha"},{"key":"ref85","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-73429-1","volume-title":"The 2005 DARPA Grand Challenge: The Great Robot Race","author":"Buehler","year":"2007"},{"key":"ref86","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-03991-1","volume-title":"The DARPA Urban Challenge: Autonomous Vehicles in City Traffic","author":"Buehler","year":"2009"},{"key":"ref87","article-title":"Mcity","year":"2015"},{"key":"ref88","article-title":"Torcs, the open racing car simulator.","author":"Team","year":"2000"},{"key":"ref89","article-title":"Beyond grand theft auto V for training, testing and enhancing deep learning in self driving cars","author":"Martinez","year":"2017"},{"key":"ref90","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy"},{"key":"ref91","article-title":"Deepdrive: A simulator that allows anyone with a PC to push the state-of-the-art in self-driving","author":"Team","year":"2020"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/2422956.2422957"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314633"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917326"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00095"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561666"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160296"},{"key":"ref99","article-title":"SLEDGE: Synthesizing simulation environments for driving agents with generative models","author":"Chitta","year":"2024"},{"key":"ref100","first-page":"10395","article-title":"TrafficSm: Learning to simulate realistic multi-agent behaviors","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Suo"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161463"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161167"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161243"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01118"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00715"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00140"},{"key":"ref108","first-page":"8556","article-title":"Megaverse: Simulating embodied agents at one million experiences per second","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Petrenko"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3331024"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2966414"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812276"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812407"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01258"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01253"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00844"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3166687"},{"key":"ref120","author":"Schoonwinkel","year":"1987","journal-title":"Design and Test of a Computer Stabilized Unicycle"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995816"},{"key":"ref122","volume-title":"Vehicle Dynamics and Control","author":"Rajamani","year":"2011"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_15"},{"key":"ref124","article-title":"NAVSIM: Data-driven non-reactive autonomous vehicle simulation","author":"Contributors","year":"2024"},{"key":"ref125","first-page":"1268","article-title":"Parting with misconceptions about learning-based vehicle motion planning","volume-title":"Proc. Conf. Robot Learn.","author":"Dauner"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref127","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Datasets Benchmarks","author":"Wilson"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref129","article-title":"Rethinking the open-loop evaluation of end-to-end autonomous driving in nuscenes","author":"Zhai","year":"2023"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01408"},{"key":"ref131","first-page":"10421","article-title":"BEVFusion: A simple and robust liDAR-camera fusion framework","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139439"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00162"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw6661"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3400227"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref138","article-title":"Carl-lead: Lidar-based end-to-end autonomous driving with contrastive deep reinforcement learning","author":"Cai","year":"2021"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3003121"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3185303"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3013234"},{"key":"ref142","article-title":"End-to-end multi-modal sensors fusion system for urban automated driving","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshops","author":"Sobh"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00615"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3214079"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00164"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2994027"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981775"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01319"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00330"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref152","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3387941"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref156","first-page":"2424","article-title":"Learning to navigate in cities without a map","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mirowski"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.41"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01084"},{"key":"ref160","first-page":"5284","article-title":"Talk to the vehicle: Language conditioned autonomous navigation of self driving cars","volume-title":"Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst.","author":"Narayanan"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00968"},{"key":"ref162","first-page":"540","article-title":"Conditional driving from natural language instructions","volume-title":"Proc. Conf. Robot Learn.","author":"Roh"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160614"},{"key":"ref164","first-page":"492","article-title":"LM-Nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Conf. Robot Learn.","author":"Shah"},{"key":"ref165","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref166","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref167","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref168","article-title":"GPT-driver: Learning to drive with GPT","author":"Mao","year":"2023"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3440097"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref171","article-title":"DriveLM: Driving with graph visual question answering","author":"Sima","year":"2023"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref173","article-title":"A survey of large language models for autonomous driving","author":"Yang","year":"2023"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11490"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"ref177","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref178","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dehghani"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3333838"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00731"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"ref184","article-title":"MapTR: Structured modeling and learning for online vectorized HD map construction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liao"},{"key":"ref185","first-page":"18873","article-title":"Openlane-v2: A topology reasoning benchmark for unified 3D HD mapping","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Datasets Benchmarks","author":"Wang"},{"key":"ref186","article-title":"Topology reasoning for driving scenes","author":"Li","year":"2023"},{"key":"ref187","article-title":"Lanesegnet: Map learning with lane segment perception for autonomous driving","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref188","article-title":"A versatile and efficient reinforcement learning framework for autonomous driving","author":"Wang","year":"2021"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340641"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827374"},{"key":"ref191","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3115235"},{"key":"ref193","first-page":"237","article-title":"Conditional affordance learning for driving in urban environments","volume-title":"Proc. Conf. Robot Learn.","author":"Sauer"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564705"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3109284"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636449"},{"key":"ref197","article-title":"Task-induced representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yamada"},{"key":"ref198","article-title":"Learning generalizable representations for reinforcement learning via adaptive meta-learner of behavioral similarities","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01390"},{"key":"ref200","article-title":"Model-predictive policy learning with uncertainty regularization for driving in dense traffic","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Henaff"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3185159"},{"key":"ref202","first-page":"23178","article-title":"Iso-dream: Isolating and leveraging noncontrollable visual dynamics in world models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref206","article-title":"Model-based imitation learning for urban driving","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00325"},{"key":"ref209","article-title":"Rethinking self-driving: Multi-task knowledge for better generalization and accident explanation ability","author":"Li","year":"2018"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1145\/3293353.3293364"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018433"},{"key":"ref213","first-page":"156","article-title":"SAM: Squeeze-and-mimic networks for conditional visual driving policy learning","volume-title":"Proc. Conf. Robot Learn.","author":"Zhao"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01657-x"},{"key":"ref215","article-title":"Explaining how a deep neural network trained with end-to-end learning steers a car","author":"Bojarski","year":"2017"},{"key":"ref216","first-page":"4701","article-title":"VisualBackPro: Efficient visualization of CNNs for autonomous driving","volume-title":"Proc. IEEE Int. Conf. Robot. Automat.","author":"Bojarski"},{"key":"ref217","article-title":"Predicting model failure using saliency maps in autonomous driving systems","author":"Mohseni","year":"2019"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.320"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813900"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794224"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00178"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10341506"},{"key":"ref223","first-page":"459","article-title":"Plant: Explainable planning transformers via object-level representations","volume-title":"Proc. Conf. Robot Learn.","author":"Renz"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422601"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996386"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_10"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01580"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00954"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108421"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"ref231","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974682"},{"key":"ref233","article-title":"Evaluating uncertainty quantification in end-to-end autonomous driving control","author":"Michelmore","year":"2018"},{"key":"ref234","first-page":"3145","article-title":"Can autonomous vehicles identify, recover from, and adapt to distribution shifts?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Filos"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968307"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3033878"},{"key":"ref237","article-title":"On a formal model of safe and scalable self-driving cars","author":"Shalev-Shwartz","year":"2017"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2021.3074645"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561894"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2024.09.058"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref242","first-page":"11698","article-title":"Causal confusion in imitation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"de Haan"},{"key":"ref243","first-page":"739","article-title":"Off-road obstacle avoidance through end-to-end learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Muller"},{"key":"ref244","article-title":"ChauffeurNet: Learning to drive by imitating the best and synthesizing the worst","author":"Bansal","year":"2019","journal-title":"Robotics: Sci. Syst. Conf"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_23"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.011"},{"key":"ref247","first-page":"872","article-title":"What is the effect of importance weighting in deep learning?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Byrd"},{"key":"ref248","article-title":"KNN approach to unbalanced data distributions: A case study involving information extraction","volume-title":"Proc. Int. Conf. Mach. Learn. Workshops","author":"Mani"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.2007853"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341538"},{"key":"ref255","article-title":"Improving the generalization of end-to-end driving through procedural generation","author":"Li","year":"2020"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref257","first-page":"9849","article-title":"Scalable end-to-end autonomous vehicle testing via rare-event simulation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"O\u2019Kelly"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793740"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3058873"},{"key":"ref260","first-page":"2357","article-title":"CAT: Closed-loop adversarial training for safe end-to-end driving","volume-title":"Proc. Conf. Robot Learn.","author":"Zhang"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/IVWorkshops54471.2021.9669228"},{"key":"ref262","article-title":"Virtual to real reinforcement learning for autonomous driving","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"You"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793668"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17251"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref267","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Matas"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196730"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14174"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref271","first-page":"2170","article-title":"Diffstack: A differentiable and modular control stack for autonomous vehicles","volume-title":"Proc. Conf. Robot Learn.","author":"Karkus"},{"key":"ref272","article-title":"Open-sourced data ecosystem in autonomous driving: The present and future","author":"Li","year":"2023"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref274","first-page":"11324","article-title":"Pathways language model (PaLM): Scaling to 540 billion parameters for breakthrough performance","volume":"24","author":"Narang","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref276","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref277","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref278","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10614862.pdf?arnumber=10614862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T19:07:33Z","timestamp":1732648053000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10614862\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":279,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3435937","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}